All Documents
3,528 documents available
PII Tokenization Pattern Research Report
Documents a pattern for intercepting PII in MCP clients, tokenizing it before model processing, and untokenizing during tool execution.
{{ page.title }}
Documents NodeLLM's built-in security features: context isolation, guardrail hooks, tool execution policies, and resource limits for production AI apps.
Tags
Lists over 2000 tags used across blog posts for categorisation and search.
Policy Specification
Defines a YAML-based policy system for governing AI agent behavior with block, allow, escalate, and redact actions.
4.5_Appendix_E
Maps AI-specific threats to SAIF components, CVEs, and CWEs for penetration testers, linking exploit paths to root causes and remediation.
PDF Scanner Python Server
Defines a FastAPI server that parses PDFs, detects and redacts PII, and stores analytics in ClickHouse.
Code Quality Report: Egnyte-LangChain Connector
Audits a LangChain connector's code quality, test coverage, security, and compliance for enterprise deployment readiness.
SunCube AI - Comprehensive Documentation
Documents a React/TypeScript EduTech platform's architecture, PostgreSQL migration, and development workflows for CTET exam prep.
Project Memory
Documents a complete RAG system for Paris cultural events with architecture, requirements, and implementation history across 15 phases.
Glossar
Defines retrieval, chunking, embedding, search, reranking, synthesis, and evaluation concepts for RAG experiments.
Golden Dataset Guidelines
Defines a structured format for a golden dataset used to benchmark, regression test, and compare retrieval-augmented generation systems.
Evaluation of RAG Systems + Presentation Outline
Outlines evaluation strategies for a RAG system and proposes a presentation structure for a project on international student queries.
PROJECT PLAN STARTER PACK - Complete Index
Maps 12 project planning sections with cross-references, fill times, and a two-week implementation workflow for a complete project charter.
LLM Evaluation
Defines a complete LLM evaluation framework covering dataset creation, automated metrics, LLM-as-judge, A/B testing, and CI regression testing.
Cassandra - AI Review Agent
> *The truth about your code. Seeing bugs before the fall of production. Ignore at your own peril.*
Agents and LLMs
Serves as a personal reference notebook covering LLM families, fine-tuning, RAG, agents, evaluation, and applied AI topics.
AWS Certified Generative AI Developer – Professional (AIP-C01)
Provides study notes and prep guidance for the AWS Certified Generative AI Developer, Professional (AIP-C01) exam, including exam style, prerequisites, and service summaries.
Project Memory
Documents a production-ready RAG system for Paris cultural events with hybrid search, LLM generation, and Streamlit UI.
AI Tester Interview Preparation Guide
Prepares candidates for an AI Tester interview focused on LLM, API, and automation testing in the pharmaceutical industry.
GenAI Benchmarks & Evaluation — Product-Based Companies
Understanding how to **benchmark, evaluate, and compare LLMs** is essential for roles at Google, OpenAI, Anthropic, Cohere, and AI research teams. This file covers the most important benchmarks, evaluation methodologies, and how to build custom evaluation harnesses.
Evaluation Framework
Defines a three-layer evaluation system for an AI investment assistant: guardrails, online RAGAS scoring, and offline golden dataset regression tests.
Understanding the Sources of Uncertainty - and Why Our Evals are Biased
Catalogues nine sources of error in AI evaluations, bias and noise, with concrete examples and statistical intuition for each.
📈 Trading RAG Mentor
Answers trading questions using your own video transcripts via a RAG pipeline with ChromaDB, LangChain, and a choice of Groq or Ollama LLMs.
RAG Deep Dive Part 7: Evaluation and Debugging RAG Systems
Teaches you to measure and debug a RAG pipeline with retrieval metrics, generation metrics, and production monitoring, all implemented from scratch in Python.